
import pandas as pd
import numpy as np
import seaborn as sns
sns.set_style('darkgrid')
import matplotlib.pyplot as plt
import plotly.graph_objects as go
import plotly.express as px
import warnings
warnings.filterwarnings('ignore')


df=pd.read_csv('D:\DATA SCIENCE Internship with CodersCave\Data\\imdb_top_1000.csv')
df.head()


df.drop(['Poster_Link', 'Overview'], axis=1,inplace=True)
df.columns

Index(['Series_Title', 'Released_Year', 'Certificate', 'Runtime', 'Genre',
       'IMDB_Rating', 'Meta_score', 'Director', 'Star1', 'Star2', 'Star3',
       'Star4', 'No_of_Votes', 'Gross'],
      dtype='object')


df.shape

(1000, 14)


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 entries, 0 to 999
Data columns (total 14 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   Series_Title   1000 non-null   object 
 1   Released_Year  1000 non-null   object 
 2   Certificate    899 non-null    object 
 3   Runtime        1000 non-null   object 
 4   Genre          1000 non-null   object 
 5   IMDB_Rating    1000 non-null   float64
 6   Meta_score     843 non-null    float64
 7   Director       1000 non-null   object 
 8   Star1          1000 non-null   object 
 9   Star2          1000 non-null   object 
 10  Star3          1000 non-null   object 
 11  Star4          1000 non-null   object 
 12  No_of_Votes    1000 non-null   int64  
 13  Gross          831 non-null    object 
dtypes: float64(2), int64(1), object(11)
memory usage: 109.5+ KB


df.isna().sum()

Series_Title       0
Released_Year      0
Certificate      101
Runtime            0
Genre              0
IMDB_Rating        0
Meta_score       157
Director           0
Star1              0
Star2              0
Star3              0
Star4              0
No_of_Votes        0
Gross            169
dtype: int64


df['Released_Year'].unique()

array(['1994', '1972', '2008', '1974', '1957', '2003', '1993', '2010',
       '1999', '2001', '1966', '2002', '1990', '1980', '1975', '2020',
       '2019', '2014', '1998', '1997', '1995', '1991', '1977', '1962',
       '1954', '1946', '2011', '2006', '2000', '1988', '1985', '1968',
       '1960', '1942', '1936', '1931', '2018', '2017', '2016', '2012',
       '2009', '2007', '1984', '1981', '1979', '1971', '1963', '1964',
       '1950', '1940', '2013', '2005', '2004', '1992', '1987', '1986',
       '1983', '1976', '1973', '1965', '1959', '1958', '1952', '1948',
       '1944', '1941', '1927', '1921', '2015', '1996', '1989', '1978',
       '1961', '1955', '1953', '1925', '1924', '1982', '1967', '1951',
       '1949', '1939', '1937', '1934', '1928', '1926', '1920', '1970',
       '1969', '1956', '1947', '1945', '1930', '1938', '1935', '1933',
       '1932', '1922', '1943', 'PG'], dtype=object)


df[df['Released_Year']=='PG']


df['Released_Year'].replace({"PG":"2019"}, inplace=True)


df['Released_Year']=df['Released_Year'].astype(int)
df['Released_Year'].dtype

dtype('int32')


df['Runtime'].dtype

dtype('O')


df['Runtime']=df['Runtime'].apply(lambda x:x.replace(" min",""))
df['Runtime']=df['Runtime'].astype(int)
df['Runtime'].dtype

dtype('int32')


df['Certificate'].isna().sum()

101


df['Certificate'].unique()

array(['A', 'UA', 'U', 'PG-13', 'R', nan, 'PG', 'G', 'Passed', 'TV-14',
       '16', 'TV-MA', 'Unrated', 'GP', 'Approved', 'TV-PG', 'U/A'],
      dtype=object)


df['Certificate'].fillna('Unrated', axis=0, inplace=True)
df['Certificate'].isna().sum()

0


df['Meta_score'].mode()

0    76.0
dtype: float64


df['Meta_score'].fillna(76.0, axis=0, inplace=True)
df['Meta_score'].isna().sum()

0


df['Meta_score'].unique()

array([ 80., 100.,  84.,  90.,  96.,  94.,  74.,  66.,  92.,  82.,  87.,
        73.,  83.,  76.,  79.,  91.,  61.,  59.,  65.,  85.,  98.,  89.,
        88.,  57.,  67.,  62.,  77.,  64.,  75.,  97.,  99.,  78.,  68.,
        81.,  95.,  69.,  55.,  70.,  58.,  86.,  71.,  63.,  93.,  72.,
        60.,  47.,  49.,  50.,  33.,  54.,  56.,  51.,  53.,  48.,  44.,
        45.,  40.,  52.,  28.,  36.,  46.,  30.,  41.])


df['Meta_score']=df['Meta_score'].astype(int)
df['Meta_score'].dtype

dtype('int32')


df['Gross'].isna().sum()

169


df['Gross'].fillna('0', axis=0, inplace=True)
df['Gross'].isna().sum()

0


df['Gross']=df['Gross'].apply(lambda x: x.replace(",",""))
df['Gross']=df['Gross'].astype(float)
df['Gross'].dtype

dtype('float64')


df['Gross'].plot(kind='box')

<AxesSubplot:>


df['Gross']=df['Gross'].replace(0, df['Gross'].median())


np.log(df['Gross']).plot(kind='kde');


df['Gross']=(df['Gross']/1000000).round(3)
df['Gross'].head()

0     28.341
1    134.966
2    534.858
3     57.300
4      4.360
Name: Gross, dtype: float64


df.head()


df.shape

(1000, 14)


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 entries, 0 to 999
Data columns (total 14 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   Series_Title   1000 non-null   object 
 1   Released_Year  1000 non-null   int32  
 2   Certificate    1000 non-null   object 
 3   Runtime        1000 non-null   int32  
 4   Genre          1000 non-null   object 
 5   IMDB_Rating    1000 non-null   float64
 6   Meta_score     1000 non-null   int32  
 7   Director       1000 non-null   object 
 8   Star1          1000 non-null   object 
 9   Star2          1000 non-null   object 
 10  Star3          1000 non-null   object 
 11  Star4          1000 non-null   object 
 12  No_of_Votes    1000 non-null   int64  
 13  Gross          1000 non-null   float64
dtypes: float64(2), int32(3), int64(1), object(8)
memory usage: 97.8+ KB


df['Series_Title'].nunique()

999


df.duplicated(['Series_Title']).sum()

1


df[df.duplicated(['Series_Title'])]


df[df['Series_Title']=='Drishyam']


df['Released_Year'].nunique()

99


df['Released_Year'].value_counts().sort_values(ascending=False)[:10]

2014    32
2004    31
2009    29
2013    28
2016    28
2001    27
2007    26
2006    26
2015    25
2012    24
Name: Released_Year, dtype: int64


df['Released_Year'].value_counts().sort_values(ascending=True)[:10]

1943    1
1920    1
1926    1
1937    1
1922    1
1930    1
1921    1
1936    1
1924    1
1941    2
Name: Released_Year, dtype: int64


movie_by_year=pd.DataFrame(df['Released_Year'].value_counts())
movie_by_year.reset_index(inplace=True)
movie_by_year.columns=['Released_Year','Number_of_Movies']
movie_by_year.head(5)


fig=px.bar(data_frame=movie_by_year, x='Released_Year', y='Number_of_Movies',
           color='Released_Year',text='Released_Year',
           title="Number of High IMDB Rated movies released by Year")
fig.show()


df['Certificate'].unique()

array(['A', 'UA', 'U', 'PG-13', 'R', 'Unrated', 'PG', 'G', 'Passed',
       'TV-14', '16', 'TV-MA', 'GP', 'Approved', 'TV-PG', 'U/A'],
      dtype=object)


plt.figure(figsize=(12,4))
sns.countplot(data=df, x='Certificate')
plt.title('Number of high rated movies by Content Type', fontsize=16, color='blue');


print("Logest Duration", df['Runtime'].max())
print("Shortest Duration", df['Runtime'].min())
print("Average Duration", df['Runtime'].mean())

Logest Duration 321
Shortest Duration 45
Average Duration 122.891


plt.figure(figsize=(12,4))
sns.distplot(df['Runtime'])
plt.title('Distribution of Runtime or Movie Duration', fontsize=16, color='blue');


df['Genre'].nunique()

202


df['Genre'].value_counts().sort_values(ascending=False)[:5].plot(kind='barh', figsize=(12,3));


print("Maximum IMDb rating", df['IMDB_Rating'].max())
print("Minimum IMDb rating", df['IMDB_Rating'].min())
print("Average IMDb rating", df['IMDB_Rating'].mean())

Maximum IMDb rating 9.3
Minimum IMDb rating 7.6
Average IMDb rating 7.949300000000012


plt.figure(figsize=(12,4))
sns.countplot(data=df, x='IMDB_Rating')
plt.title('Number of high rated movies by IMDb Rating', fontsize=16, color='blue');


print("Least Meta score for Movie",df['Meta_score'].min())
print("Highest Meta score for Movie",df['Meta_score'].max())
print("Average Meta score for movie", df['Meta_score'].mean())

Least Meta score for Movie 28
Highest Meta score for Movie 100
Average Meta score for movie 77.662


plt.figure(figsize=(12,4))
sns.countplot(df['Meta_score'])
plt.title('Number of high rated movies by Meta Score', fontsize=16, color='blue')
plt.xticks(rotation=90);


print("Maximum Votes for Movie", df['No_of_Votes'].max())
print("Minimum Votes for Movie", df['No_of_Votes'].min())

Maximum Votes for Movie 2343110
Minimum Votes for Movie 25088


plt.figure(figsize=(12,4))
sns.distplot(df['No_of_Votes'])
plt.title('Distribution of Votes', fontsize=16, color='blue')
plt.xticks(rotation=90);


print("Maximum Gross in Million for Movie", df['Gross'].max())
print("Minimum Gross in Million for Movie", df['Gross'].min())

Maximum Gross in Million for Movie 936.662
Minimum Gross in Million for Movie 0.001


plt.figure(figsize=(12,4))
sns.distplot(df['Gross'])
plt.title('Distribution of Gross in Million', fontsize=16, color='blue')
plt.xticks(rotation=90);


df['Director'].nunique()

548


(df['Director'].value_counts()[:10]).plot(kind='barh', figsize=(12,4));


star1=pd.DataFrame(df['Star1'].value_counts())
star1.reset_index(inplace=True)
star1.columns=['Star','no_of_movie1']
star1.head()


star2=pd.DataFrame(df['Star2'].value_counts())
star2.reset_index(inplace=True)
star2.columns=['Star','no_of_movie2']
star2.head()


star3=pd.DataFrame(df['Star3'].value_counts())
star3.reset_index(inplace=True)
star3.columns=['Star','no_of_movie3']
star3.head()


star4=pd.DataFrame(df['Star4'].value_counts())
star4.reset_index(inplace=True)
star4.columns=['Star','no_of_movie4']
star4.head()


star=pd.concat([star1,star2, star3, star4], axis=0)
star.head()


star.fillna(0, axis=0, inplace=True)


star['In_Movies']=star['no_of_movie1']+star['no_of_movie2']+star['no_of_movie3']+star['no_of_movie4']
star.drop(['no_of_movie1','no_of_movie2','no_of_movie3','no_of_movie4'], axis=1, inplace=True)
star.head()


star_in_movies=pd.pivot_table(data=star, 
                              index='Star', aggfunc='max',
                              values='In_Movies').sort_values(by='In_Movies', ascending=False)[:20]
star_in_movies


star_in_movies.reset_index(inplace=True)
fig=px.bar(data_frame=star_in_movies, x='Star', y='In_Movies',
           color='Star',text='In_Movies',
           title="Actors Stared in Number of High IMDB Rated movies")
fig.show()


top_10_pop = df[['Star1','Star2','Star3', 'Star4']].values.tolist()[:10]
top_10_pop

[['Tim Robbins', 'Morgan Freeman', 'Bob Gunton', 'William Sadler'],
 ['Marlon Brando', 'Al Pacino', 'James Caan', 'Diane Keaton'],
 ['Christian Bale', 'Heath Ledger', 'Aaron Eckhart', 'Michael Caine'],
 ['Al Pacino', 'Robert De Niro', 'Robert Duvall', 'Diane Keaton'],
 ['Henry Fonda', 'Lee J. Cobb', 'Martin Balsam', 'John Fiedler'],
 ['Elijah Wood', 'Viggo Mortensen', 'Ian McKellen', 'Orlando Bloom'],
 ['John Travolta', 'Uma Thurman', 'Samuel L. Jackson', 'Bruce Willis'],
 ['Liam Neeson', 'Ralph Fiennes', 'Ben Kingsley', 'Caroline Goodall'],
 ['Leonardo DiCaprio', 'Joseph Gordon-Levitt', 'Elliot Page', 'Ken Watanabe'],
 ['Brad Pitt', 'Edward Norton', 'Meat Loaf', 'Zach Grenier']]


plt.figure(figsize=(12,6))
sns.barplot(data=df, y='Series_Title', x='Runtime', ci=None, 
           order=df.groupby('Series_Title').Runtime.max().sort_values(ascending=False)[:10].index)
plt.title("Top 10 Logest Duration Movies", fontsize=16, color='blue');


plt.figure(figsize=(12,6))
sns.barplot(data=df, y='Series_Title', x='Runtime', ci=None, 
           order=df.groupby('Series_Title').Runtime.max().sort_values(ascending=True)[:10].index)
plt.title("Top 10 shorter Duration Movies", fontsize=16, color='blue');


avg_runtime=pd.DataFrame(df.groupby('Released_Year').Runtime.mean())
avg_runtime.reset_index(inplace=True)
avg_runtime.columns=['Released_Year','Runtime']
avg_runtime.head()


fig=px.line(data_frame=avg_runtime, x='Released_Year', y='Runtime',
           title="Average runtime of High IMDB Rated movies by each year")
fig.show()


avg_rating=pd.DataFrame(df.groupby('Released_Year').IMDB_Rating.mean())
avg_rating.reset_index(inplace=True)
avg_rating.columns=['Released_Year','IMDB_Rating']
avg_rating.head()


fig=px.line(data_frame=avg_rating, x='Released_Year', y='IMDB_Rating',
           title="Average IMDB Rating by each year")
fig.show()


plt.figure(figsize=(12,6))
sns.barplot(data=df, y='Series_Title', x='IMDB_Rating', ci=None, 
           order=df.groupby('Series_Title').IMDB_Rating.max().sort_values(ascending=False)[:10].index)
plt.xticks(np.arange(0,10,0.5))
plt.title("Top 10 Movies by IMDB Rating", fontsize=16, color='blue');


plt.figure(figsize=(12,6))
sns.barplot(data=df, y='Series_Title', x='Meta_score', ci=None, 
           order=df.groupby('Series_Title').Meta_score.max().sort_values(ascending=False)[:10].index)
plt.title("Top 10 Movies by Meta Score", fontsize=16, color='blue');


plt.figure(figsize=(12,6))
sns.barplot(data=df, y='Series_Title', x='No_of_Votes', ci=None, 
           order=df.groupby('Series_Title').No_of_Votes.max().sort_values(ascending=False)[:10].index)
plt.title("Top 10 Movies by No of Votes", fontsize=16, color='blue');


plt.figure(figsize=(12,6))
sns.barplot(data=df, y='Series_Title', x='Gross', ci=None, 
           order=df.groupby('Series_Title').Gross.max().sort_values(ascending=False)[:10].index)
plt.title("Top 10 Movies by Total Gross Net", fontsize=16, color='blue');


fig=px.scatter(data_frame=df, x='Runtime', y='IMDB_Rating', color='Released_Year',
           title="Runtime vs IMDB Rating")
fig.show()


num_feature=['Released_Year','Runtime','Meta_score','IMDB_Rating','No_of_Votes','Gross']


plt.figure(figsize=(12,6))
sns.heatmap(df[num_feature].corr(), cmap='Blues', annot=True);
plt.title("Correlation betweeen Numerical Features", fontsize=18, color='blue');


fig=px.scatter(data_frame=df, x='No_of_Votes', y='IMDB_Rating', color='Released_Year',
           title="No_of_Votes vs IMDB Rating")
fig.show()


fig=px.scatter(data_frame=df, y='Gross', x='IMDB_Rating', color='Released_Year',
           title="Gross vs IMDB Rating")
fig.show()


runtime_by_genre=pd.DataFrame(df.groupby('Genre').Runtime.mean().sort_values(ascending=False)[:10])
runtime_by_genre.reset_index(inplace=True)
runtime_by_genre.columns=['Genre','Runtime']
runtime_by_genre.head()


fig=px.bar(data_frame=runtime_by_genre, x='Genre', y='Runtime', color='Genre',
           title="Top 10 Genre with high Average Run time", text='Runtime')
fig.show()


runtime_by_genre=pd.DataFrame(df.groupby('Genre').Runtime.mean().sort_values(ascending=True)[:10])
runtime_by_genre.reset_index(inplace=True)
runtime_by_genre.columns=['Genre','Runtime']
runtime_by_genre.head()


fig=px.bar(data_frame=runtime_by_genre, x='Genre', y='Runtime', color='Genre',
           title="Top 10 Genre with least Average Run time", text='Runtime')
fig.show()


rating_by_genre=pd.DataFrame(df.groupby('Genre').IMDB_Rating.mean().sort_values(ascending=False)[:10])
rating_by_genre.reset_index(inplace=True)
rating_by_genre.columns=['Genre','IMDB_Rating']
rating_by_genre.head()


fig=px.bar(data_frame=rating_by_genre, x='Genre', y='IMDB_Rating', color='Genre',
           title="Top 10 Genre with highest IMDB Rating", text='IMDB_Rating')
fig.show()


rating_by_genre=pd.DataFrame(df.groupby('Genre').IMDB_Rating.mean().sort_values(ascending=True)[:10])
rating_by_genre.reset_index(inplace=True)
rating_by_genre.columns=['Genre','IMDB_Rating']
rating_by_genre.head()


fig=px.bar(data_frame=rating_by_genre, x='Genre', y='IMDB_Rating', color='Genre',
           title="Top 10 Genre with least IMDB Rating", text='IMDB_Rating')
fig.show()


metascore_by_genre=pd.DataFrame(df.groupby('Genre').Meta_score.mean().sort_values(ascending=False)[:10])
metascore_by_genre.reset_index(inplace=True)
metascore_by_genre.columns=['Genre','Meta_score']
metascore_by_genre.head()


fig=px.bar(data_frame=metascore_by_genre, x='Genre', y='Meta_score', color='Genre',
           title="Top 10 Genre with High Average Meta Score", text='Meta_score')
fig.show()


votes_by_genre=pd.DataFrame(df.groupby('Genre').No_of_Votes.mean().sort_values(ascending=False)[:10])
votes_by_genre.reset_index(inplace=True)
votes_by_genre.columns=['Genre','No_of_Votes']
votes_by_genre.head()


fig=px.bar(data_frame=votes_by_genre, x='Genre', y='No_of_Votes', color='Genre',
           title="Top 10 Genre with High Average Votes Received", text='No_of_Votes')
fig.show()


gross_by_genre=pd.DataFrame(df.groupby('Genre').Gross.mean().sort_values(ascending=False)[:10])
gross_by_genre.reset_index(inplace=True)
gross_by_genre.columns=['Genre','Gross']
gross_by_genre.head()


fig=px.bar(data_frame=gross_by_genre, x='Genre', y='Gross', color='Genre',
           title="Top 10 Genre with High average Grossing", text='Gross')
fig.show()


certificate_by_votes=pd.DataFrame(df.groupby('Certificate').No_of_Votes.mean().sort_values(ascending=False))
certificate_by_votes.reset_index(inplace=True)
certificate_by_votes.columns=['Certificate','No_of_Votes']
certificate_by_votes.head()


fig=px.bar(data_frame=certificate_by_votes, x='Certificate', y='No_of_Votes', color='Certificate',
           title="Top 10 Certificate or Content type by High Average Votes Received", text='No_of_Votes')
fig.show()


certificate_by_gross=pd.DataFrame(df.groupby('Certificate').Gross.mean().sort_values(ascending=False))
certificate_by_gross.reset_index(inplace=True)
certificate_by_gross.columns=['Certificate','Gross']
certificate_by_gross.head()


fig=px.bar(data_frame=certificate_by_gross, x='Certificate', y='Gross', color='Certificate',
           title="Top 10 Certificate or Content type by High Average Gross", text='Gross')
fig.show()


director_by_rating=pd.DataFrame(df.groupby('Director').IMDB_Rating.mean().sort_values(ascending=False)[:10])
director_by_rating.reset_index(inplace=True)
director_by_rating.columns=['Director','IMDB_Rating']
director_by_rating.head()


fig=px.bar(data_frame=director_by_rating, x='IMDB_Rating', y='Director', color='Director',
           title="Top 10 Directors by High Average IMDB Rating", text='IMDB_Rating')
fig.show()


director_by_gross=pd.DataFrame(df.groupby('Director').Gross.sum().sort_values(ascending=False)[:10])
director_by_gross.reset_index(inplace=True)
director_by_gross.columns=['Director','Gross']
director_by_gross.head()


fig=px.bar(data_frame=director_by_gross, x='Gross', y='Director', color='Director',
           title="Top 10 Directors by Total Gross Net", text='Gross')
fig.show()


dd=pd.DataFrame(df.groupby(['Series_Title','Director','Star1','Star2','Star3','Star4']).Gross.max().sort_values(ascending=False)[:5])
dd

	Poster_Link	Series_Title	Released_Year	Certificate	Runtime	Genre	IMDB_Rating	Overview	Meta_score	Director	Star1	Star2	Star3	Star4	No_of_Votes	Gross
0	https://m.media-amazon.com/images/M/MV5BMDFkYT...	The Shawshank Redemption	1994	A	142 min	Drama	9.3	Two imprisoned men bond over a number of years...	80.0	Frank Darabont	Tim Robbins	Morgan Freeman	Bob Gunton	William Sadler	2343110	28,341,469
1	https://m.media-amazon.com/images/M/MV5BM2MyNj...	The Godfather	1972	A	175 min	Crime, Drama	9.2	An organized crime dynasty's aging patriarch t...	100.0	Francis Ford Coppola	Marlon Brando	Al Pacino	James Caan	Diane Keaton	1620367	134,966,411
2	https://m.media-amazon.com/images/M/MV5BMTMxNT...	The Dark Knight	2008	UA	152 min	Action, Crime, Drama	9.0	When the menace known as the Joker wreaks havo...	84.0	Christopher Nolan	Christian Bale	Heath Ledger	Aaron Eckhart	Michael Caine	2303232	534,858,444
3	https://m.media-amazon.com/images/M/MV5BMWMwMG...	The Godfather: Part II	1974	A	202 min	Crime, Drama	9.0	The early life and career of Vito Corleone in ...	90.0	Francis Ford Coppola	Al Pacino	Robert De Niro	Robert Duvall	Diane Keaton	1129952	57,300,000
4	https://m.media-amazon.com/images/M/MV5BMWU4N2...	12 Angry Men	1957	U	96 min	Crime, Drama	9.0	A jury holdout attempts to prevent a miscarria...	96.0	Sidney Lumet	Henry Fonda	Lee J. Cobb	Martin Balsam	John Fiedler	689845	4,360,000

	Star	no_of_movie2
0	Emma Watson	7
1	Matt Damon	5
2	Kate Winslet	4
3	Ian McKellen	4
4	Chris Evans	4

	Star	no_of_movie3
0	Rupert Grint	5
1	Scarlett Johansson	4
2	Jennifer Connelly	4
3	Rachel McAdams	4
4	John Goodman	4

	Star	no_of_movie4
0	Michael Caine	4
1	Mark Ruffalo	3
2	Catherine Keener	3
3	Julianne Moore	2
4	Donald Sutherland	2

	Star	no_of_movie1	no_of_movie2	no_of_movie3	no_of_movie4
0	Tom Hanks	12.0	NaN	NaN	NaN
1	Robert De Niro	11.0	NaN	NaN	NaN
2	Al Pacino	10.0	NaN	NaN	NaN
3	Clint Eastwood	10.0	NaN	NaN	NaN
4	Humphrey Bogart	9.0	NaN	NaN	NaN

	Series_Title	Released_Year	Certificate	Runtime	Genre	IMDB_Rating	Meta_score	Director	Star1	Star2	Star3	Star4	No_of_Votes	Gross
87	Drishyam	2013	U	160	Crime, Drama, Thriller	8.3	76	Jeethu Joseph	Mohanlal	Meena	Asha Sharath	Ansiba	30722	10.703
136	Drishyam	2015	UA	163	Crime, Drama, Mystery	8.2	76	Nishikant Kamat	Ajay Devgn	Shriya Saran	Tabu	Rajat Kapoor	70367	0.739

	Genre	Runtime
0	Adventure, Drama, Musical	224.00
1	Drama, History, Romance	181.50
2	Drama, Family, Musical	181.00
3	Adventure, Drama, History	177.25
4	Biography, Drama, War	172.00

	Genre	Runtime
0	Comedy, Musical, War	69.0
1	Animation, Sci-Fi	72.0
2	Fantasy, Horror, Mystery	76.0
3	Animation, Comedy, Fantasy	81.0
4	Animation, Crime, Mystery	81.0

	Genre	IMDB_Rating
0	Animation, Drama, War	8.50
1	Drama, Musical	8.40
2	Action, Sci-Fi	8.40
3	Drama, Mystery, War	8.35
4	Western	8.35

	Genre	IMDB_Rating
0	Animation, Drama, Romance	7.6
1	Adventure, Comedy, War	7.6
2	Drama, War, Western	7.6
3	Animation, Comedy, Crime	7.6
4	Action, Adventure, Mystery	7.6

	Genre	Meta_score
0	Mystery, Romance, Thriller	100.0
1	Comedy, Musical, Romance	99.0
2	Adventure, Mystery, Thriller	98.0
3	Drama, Fantasy, War	98.0
4	Comedy, Music, Romance	98.0

	Genre	No_of_Votes
0	Action, Sci-Fi	1.157242e+06
1	Action, Adventure, Fantasy	9.547677e+05
2	Action, Adventure	9.255334e+05
3	Adventure, Drama, Sci-Fi	9.125223e+05
4	Action, Drama, Sci-Fi	8.403165e+05

	Genre	Gross
0	Family, Sci-Fi	435.111000
1	Action, Adventure, Fantasy	352.723500
2	Action, Adventure, Family	301.959000
3	Action, Adventure, Sci-Fi	280.888524
4	Adventure, Fantasy	280.685500

	Certificate	No_of_Votes
0	UA	439032.582857
1	A	428215.045685
2	U	256106.358974
3	R	212991.869863
4	PG-13	144101.976744

	Certificate	Gross
0	UA	122.887000
1	U	76.124855
2	A	59.297640
3	G	43.114083
4	PG-13	34.506535

	In_Movies
Star
Tom Hanks	12.0
Robert De Niro	11.0
Al Pacino	10.0
Clint Eastwood	10.0
Humphrey Bogart	9.0
Leonardo DiCaprio	9.0
James Stewart	8.0
Johnny Depp	8.0
Christian Bale	8.0
Emma Watson	7.0
Denzel Washington	7.0
Toshirô Mifune	7.0
Aamir Khan	7.0
Charles Chaplin	6.0
Daniel Radcliffe	6.0
Tom Cruise	6.0
Jake Gyllenhaal	6.0
Ethan Coen	6.0
Cary Grant	6.0
Dustin Hoffman	5.0

	Director	IMDB_Rating
0	Frank Darabont	8.95
1	Irvin Kershner	8.70
2	Lana Wachowski	8.70
3	George Lucas	8.60
4	Roberto Benigni	8.60

	Director	Gross
0	Steven Spielberg	2478.135
1	Anthony Russo	2205.039
2	Christopher Nolan	1937.453
3	James Cameron	1748.236
4	Peter Jackson	1597.313

						Gross
Series_Title	Director	Star1	Star2	Star3	Star4
Star Wars: Episode VII - The Force Awakens	J.J. Abrams	Daisy Ridley	John Boyega	Oscar Isaac	Domhnall Gleeson	936.662
Avengers: Endgame	Anthony Russo	Joe Russo	Robert Downey Jr.	Chris Evans	Mark Ruffalo	858.373
Avatar	James Cameron	Sam Worthington	Zoe Saldana	Sigourney Weaver	Michelle Rodriguez	760.508
Avengers: Infinity War	Anthony Russo	Joe Russo	Robert Downey Jr.	Chris Hemsworth	Mark Ruffalo	678.815
Titanic	James Cameron	Leonardo DiCaprio	Kate Winslet	Billy Zane	Kathy Bates	659.325

Data Analysis on Top 1000 Movies by IMDB Rating¶

Import required libraries¶

Load the dataset¶

Column Information¶

Poster link and Overview are not needed for our analysis, drop this column.¶

Missing values¶

Data Cleaning¶

Convert Release_Year to Int so that we can perform some time series analysis.¶

There is one entry in released year column "PG" lets see what is is.¶

From internet i found that "Apollo 13" movie released in year 2019, replace "PG" with "2019"¶

Convert Runtime column to numeric type¶

Filling the missing values in Certificate column¶

Filling missing values in Meta Score column¶

Meta score is from 0 to 100 so this is a descrete contineous column so Fill the missing values which Mode of this column.¶

Convert Meta Score to numerical type¶

Fill missing values in Gross columns¶

FIlling missing values with 0 and then converting the column to numeric and then check the outliers and then decide which statistic value is best fit to fill the missing values.¶

Check for outliers¶

Convert Gross into Million scale¶

Cleaned Data¶

Exploratory Data Analysis¶

Univariate analysis¶

Analyze Series_Title¶

Analyze Resease Year¶

In which calender year most of high IMDB rated movies are released?¶

In which calender year lest of high IMDB rated movies are released?¶

Count of most rated IMDB movies by Year¶

Analyze Certificate or Content Rating column.¶

Which Content Type(Certificate) has most high rated movies.¶

Analyze Runtime¶

What is logest, shortest and average movie duration for top rated movies?¶

Distribution of Runtime or Movie Duration¶

Analyze Genre¶

Top 5 Genres with highest number of high rated movies.¶

Analyze IMDB rating¶

Analyze Metascore¶

Analyze Number of Votes¶

Analyze Gross¶

Aalyze Director column¶

Which director gave most top rated movies¶

Analyze Star/Casts column¶

There 4 top Stars in each movie. Lets create a seperate dataframe to check the actor who working in many top rated movies.¶

Top 4 Popular actors¶

Bivariate and Multivariate analaysis.¶

Name the top 10 longest duration movie?¶

Name the top 10 least duration movie?¶

What is the average runtime by each year?¶

What is the average IMDB rating by each year?¶

Name the Movies with high IMDB rating?¶

Name the Movies with high Meta score?¶

Which Movie recieved highest Votes.¶

Name the Top 10 Highesr Grossing Movies¶

Relationship between Runtime and IMDB Rating¶

Is there any relation between Released Year, Runtime, IMDB Rating, Meta Score, Votes and Gross?¶

Relationship between Votes and IMDB Rating¶

Relationship between IMDB rating and Gross.¶

Top 10 Genre with high Average Run time¶

Top 10 Genre with least Average Run time¶

Top 10 Genres with high Average IMDB Rating¶

Top 10 Genres with least Average IMDB Rating¶

Top 10 Genres with high Average Meta Score¶

Top 10 Genres with high Average Votes recieved.¶

Top 10 Genres by highest average Gross Net¶

Top Content Type(Certificate) by average Number of Votes¶

Top Content Type(Certificate) by average Grossing¶

Name the top 10 Director with highest average IMDB Rating¶

Top 10 Director with high Gross collection¶

Name the top 5 Director and Stars who worked in high Grossing Movies.¶

Summary/Conclusion¶